Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization

2 Jun 2020Mayumi OhtaNathaniel BergerArtem SokolovStefan Riezler

Interest in stochastic zeroth-order (SZO) methods has recently been revived in black-box optimization scenarios such as adversarial black-box attacks to deep neural networks. SZO methods only require the ability to evaluate the objective function at random input points, however, their weakness is the dependency of their convergence speed on the dimensionality of the function to be evaluated... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.